Local density adaptive similarity measurement for spectral clustering

Authors:
Xianchao Zhang;Jingwei Li;Hong Yu
Affiliations:
School of Software, Dalian University of Technology, Dalian 116620, China;School of Software, Dalian University of Technology, Dalian 116620, China;School of Software, Dalian University of Technology, Dalian 116620, China
Venue:
Pattern Recognition Letters
Year:
2011

Citing 9
Cited 1

Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Min-max Cut Algorithm for Graph Partitioning and Data Clustering

ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Between Min Cut and Graph Bisection

MFCS '93 Proceedings of the 18th International Symposium on Mathematical Foundations of Computer Science
Path-Based Clustering for Grouping of Smooth Curves and Texture Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cluster ensembles --- a knowledge reuse framework for combining multiple partitions

The Journal of Machine Learning Research
Robust path-based spectral clustering

Pattern Recognition
A tutorial on spectral clustering

Statistics and Computing
Backpropagation applied to handwritten zip code recognition

Neural Computation
On defining affinity graph for spectral clustering through ranking on manifolds

Neurocomputing

Vector quantization based approximate spectral clustering of large datasets

Pattern Recognition

Quantified Score

Hi-index	0.10

Visualization

Abstract

Similarity measurement is crucial to the performance of spectral clustering. The Gaussian kernel function is usually adopted as the similarity measure. However, with a fixed kernel parameter, the similarity between two data points is only determined by their Euclidean distance, and is not adaptive to their surroundings. In this paper, a local density adaptive similarity measure is proposed, which uses the local density between two data points to scale the Gaussian kernel function. The proposed similarity measure satisfies the clustering assumption and has an effect of amplifying intra-cluster similarity, thus making the affinity matrix clearly block diagonal. Experimental results on both synthetic and real world data sets show that the spectral clustering algorithm with our local density adaptive similarity measure outperforms the traditional spectral clustering algorithm, the path-based spectral clustering algorithm and the self-tuning spectral clustering algorithm.